UCL Discovery

Abstract

We present an algorithm for learning stable machines which is motivated by recent results in statistical learning theory. The algorithm is similar to Breiman's bagging despite some important differences in that it computes an ensemble combination of machines trained on small random sub-samples of an initial training set. A remarkable property is that it is often possible to just use the empirical error of these combinations of machines for model selection. We report experiments using support vector machines and neural networks validating the theory.